changeset 4:4494c973f643 draft default tip

Deleted selected files
author testtool
date Fri, 13 Oct 2017 10:15:08 -0400
parents a5a5716e0317
children
files accuracy.R accuracy.xml
diffstat 2 files changed, 0 insertions(+), 104 deletions(-) [+]
line wrap: on
line diff
--- a/accuracy.R	Fri Oct 13 10:14:29 2017 -0400
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,48 +0,0 @@
-require(caret, quietly = TRUE)
-
-args <- commandArgs(trailingOnly = TRUE)
-
-input = args[1]
-p = args[2]   
-output1 = args[3] 
-output2 = args[4] 
-
-dataset <- read.csv(input, header=TRUE)
-
-validation_index <- createDataPartition(dataset$Species, p=p, list=FALSE)
-
-validation <- dataset[-validation_index,]
-
-validdataset <- dataset[validation_index,]
-
-percentage <- prop.table(table(validdataset$Species)) * 100
-cbind(freq=table(validdataset$Species), percentage=percentage)
-
-output_summary <- summary(validdataset) 
-write.csv(output_summary,output1)
-
-control <- trainControl(method="cv", number=10)
-metric <- "Accuracy"
-
-# a) linear algorithms
-set.seed(7)
-fit.lda <- train(Species~., data=validdataset, method="lda", metric=metric, trControl=control)
-# b) nonlinear algorithms
-# CART
-set.seed(7)
-fit.cart <- train(Species~., data=validdataset, method="rpart", metric=metric, trControl=control)
-# kNN
-set.seed(7)
-fit.knn <- train(Species~., data=validdataset, method="knn", metric=metric, trControl=control)
-# c) advanced algorithms
-# SVM
-set.seed(7)
-fit.svm <- train(Species~., data=validdataset, method="svmRadial", metric=metric, trControl=control)
-# Random Forest
-set.seed(7)
-fit.rf <- train(Species~., data=validdataset, method="rf", metric=metric, trControl=control)
-
-results <- resamples(list(lda=fit.lda, cart=fit.cart, knn=fit.knn, svm=fit.svm, rf=fit.rf))
-output_results <- summary(results) 
-
-write.csv(as.matrix(output_results),output2)
--- a/accuracy.xml	Fri Oct 13 10:14:29 2017 -0400
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,56 +0,0 @@
-<tool id="accuracy" name="accuracy" version="1.0.0">
-    <description>model creation and accuracy estimation</description>
-    <requirements>
-        <requirement type="package" version="6.0_76">r-caret</requirement>
-    </requirements>
-    <command detect_errors="aggressive">
-        Rscript '$__tool_directory__/accuracy.R' '$input' '$p' '$output1' '$output2' 
-    </command>
-<inputs>
-        <param format="csv" type="data" name="input"  value="" label="Input dataset" help="
-   e.g. iris species table 
-Sepal.Length,Sepal.Width,Petal.Length,Petal.Width,Species
-5.1,3.5,1.4,0.2,Iris-setosa
-4.9,3,1.4,0.2,Iris-setosa
-4.7,3.2,1.3,0.2,Iris-setosa
-4.6,3.1,1.5,0.2,Iris-setosa''"/>
- <param name="p" type="integer" value="0.80" label="Select % of data to training and testing the models"/>   
- </inputs>
-    <outputs>
-        <data format="csv" name="output1" label="dataset_summary.csv" />
-        <data format="csv" name="output2" label="accuracy_summary.csv" />
-    </outputs>
- <tests>
-    <test>
-      <param name="test">
-      <element name="test-data">
-          <collection type="data">
-                <element format="csv" name="input" label="test-data/input.csv"/>
-          </collection>
-        </element>
-        </param>
-        <output format="csv"  name="fit" label="test-data/dataset_summary.csv"/>
-        <output format="csv"  name="fit" label="test-data/accuracy_summary.csv"/>
-        </test>
-    </tests>
-  <help>
-Tool allow us to build 5 different models to predict e.g. species from flower measurements.
-In the end we can select the best model for further analysis.
-
-Let’s evaluate 5 different algorithms:
-  
-**Linear Discriminant Analysis (LDA)**
-**Classification and Regression Trees (CART).**
-**k-Nearest Neighbors (kNN).**
-**Support Vector Machines (SVM) with a linear kernel.**
-**Random Forest (RF)**
-
-This is a good mixture of simple linear (LDA), nonlinear (CART, kNN) and complex nonlinear methods (SVM, RF). 
-We reset the random number seed before reach run to ensure that the evaluation of each algorithm is performed
-using exactly the same data splits. It ensures the results are directly comparable.
-
-</help>
-<citations>
- <citation>https://CRAN.R-project.org/package=caret</citation>
-</citations>
-</tool>